Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nobilix/twenty-crm-skill --skill twenty-crmgit clone --depth 1 https://github.com/nobilix/twenty-crm-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm)<a href="https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm"><img src="https://agentmods.dev/badge/skills/nobilix/twenty-crm-skill/twenty-crm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm"><img src="https://agentmods.dev/badge/skills/nobilix/twenty-crm-skill/twenty-crm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00148 | $0.02781 |
| Opus 5 | $0.00074 | $0.01391 |
| Sonnet 5 | $0.00030 | $0.00556 |
| Haiku 4.5 | $0.00015 | $0.00278 |
Grade A, and why
twenty-crm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twenty CRM
Reusable across any Twenty deployment. The skill drives ocli — a CLI generated from your workspace's OpenAPI spec. Per-instance state is an ocli profile under ~/.ocli/; the skill keeps only a one-line pointer in ~/.config/twenty-cli/config.json. Nothing is hardcoded.
Step 0: preflight (always)
node scripts/twenty.mjs preflight
STATUS=ready→ proceed. Output also givesPROFILE=<name>(the ocli profile, usuallytwenty),URL=<base-url>(use it to build UI links), andMETADATA=<name>if the metadata profile was set up.- non-zero exit → not configured. Stderr prints the two things setup needs (URL, API key) and the two setup paths below; pick by context. For the full walkthrough load
references/setup-guide.md.
not_ready is not sticky. Setup happens in the user's own terminal, so a config that didn't exist this turn may exist the next. If you reported not_ready and the user comes back with any CRM request, re-run preflight first — don't repeat the "not configured" message from memory.
Setup
Idempotent — re-running updates the existing profile. New here? references/setup-guide.md has the full step-by-step (where the URL comes from, how to create the API key).
You need: the URL you open Twenty at — self-hosted https://crm.your-company.com or cloud https://your-workspace.twenty.com (the workspace subdomain, not api.twenty.com — that host has no UI, so record links break); setup appends /rest. Plus an API key from Settings → APIs & Webhooks → + Create key.
Recommend the user run setup in their own terminal — the API key is typed as hidden input, so it never lands in the chat transcript. Tell them why, and give them:
node <skill-path>/scripts/twenty.mjs setup
That's the safe default. Only if the user themselves puts the URL + key in chat (or explicitly asks you to run it) use the non-interactive form:
node <skill-path>/scripts/twenty.mjs setup --non-interactive --url <url> --token <key>
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 184 lines · 148 tokens per session scan A 10fd9d72d1e2
twenty-crm is a skill published in the GitHub repository nobilix/twenty-crm-skill (11 stars, last pushed 3mo ago), licensed MIT. It adds 148 tokens to every session and 2,781 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…